arXiv subjects

Yingying Chen

Publications and source records attributed to Yingying Chen.

At least 37 records · Page 2Linked to original sources

arXiv2024

LINK: Adaptive Modality Interaction for Audio-Visual Video Parsing

Audio-visual video parsing focuses on classifying videos through weak labels while identifying events as either visible, audible, or both, alongside their respective temporal boundaries. Many methods ignore that different modalities often lack alignment, thereby introducing extra noise during modal interaction. In this work, we introduce a Learning Interaction method for Non-aligned Knowledge (LINK), designed to equilibrate the contributions of distinct modalities by dynamically adjusting their input during event prediction. Additionally, we leverage the semantic information of pseudo-labels as a priori knowledge to mitigate noise from other modalities. Our experimental findings demonstrate that our model outperforms existing methods on the LLP dataset.

cs.CV↗

arXiv2024

Precision Profile Pollution Attack on Sequential Recommenders via Influence Function

Sequential recommendation approaches have demonstrated remarkable proficiency in modeling user preferences. Nevertheless, they are susceptible to profile pollution attacks (PPA), wherein items are introduced into a user's interaction history deliberately to influence the recommendation list. Since retraining the model for each polluted item is time-consuming, recent PPAs estimate item influence based on gradient directions to identify the most effective attack candidates. However, the actual item representations diverge significantly from the gradients, resulting in disparate outcomes.To tackle this challenge, we introduce an INFluence Function-based Attack approach INFAttack that offers a more accurate estimation of the influence of polluting items. Specifically, we calculate the modifications to the original model using the influence function when generating polluted sequences by introducing specific items. Subsequently, we choose the sequence that has been most significantly influenced to substitute the original sequence, thus promoting the target item. Comprehensive experiments conducted on five real-world datasets illustrate that INFAttack surpasses all baseline methods and consistently delivers stable attack performance for both popular and unpopular items.

cs.IR↗

arXiv2024

MROVSeg: Breaking the Resolution Curse of Vision-Language Models in Open-Vocabulary Image Segmentation

Pretrained vision-language models (VLMs), \eg CLIP, are increasingly used to bridge the gap between open- and close-vocabulary recognition in open-vocabulary image segmentation. As VLMs are generally pretrained with low-resolution images (e.g. $224\times224$), most previous methods operate only on downscaled images. We question this design as low resolution features often fail to preserve fine details. A typical solution is to employ additional image backbones for high-resolution inputs, but it also introduce significant computation overhead. Therefore, we propose MROVSeg, a multi-resolution training framework for open-vocabulary image segmentation with a single pretrained CLIP backbone, that uses sliding windows to slice the high-resolution input into uniform patches, each matching the input size of the well-trained image encoder. Its key components include a Multi-Res Adapter, which restores the spatial geometry and grasps local-global correspondences across patches by interacting with multi-resolution features. To achieve accurate segmentation, we introduce Multi-grained Masked Attention scheme to aggregate multi-grained semantics from multi-resolution CLIP features to object queries. Through comprehensive experiments, we demonstrate the superiority of MROVSeg on well-established open-vocabulary image segmentation benchmarks, establishing new standards for open-vocabulary image segmentation.

cs.CV↗

arXiv2024

The BRAVO Semantic Segmentation Challenge Results in UNCV2024

We propose the unified BRAVO challenge to benchmark the reliability of semantic segmentation models under realistic perturbations and unknown out-of-distribution (OOD) scenarios. We define two categories of reliability: (1) semantic reliability, which reflects the model's accuracy and calibration when exposed to various perturbations; and (2) OOD reliability, which measures the model's ability to detect object classes that are unknown during training. The challenge attracted nearly 100 submissions from international teams representing notable research institutions. The results reveal interesting insights into the importance of large-scale pre-training and minimal architectural design in developing robust and reliable semantic segmentation models.

cs.CV↗

arXiv2024

Out-of-plane orientated self-trapped excitons enabled polarized light guiding in 2D perovskites

Active optical waveguides combine light source and waveguides together in an individual component, which are essential for the integrated photonic chips. Although 1D luminescent materials based optical waveguides were extensively investigated, 2D waveguides allow photons to flow within a plane and serve as an ideal component for the ultracompact photonic circuits. Nevertheless, light guiding in 2D planar structures normally relies on the precise control of molecular orientation, which is complicated and low yield. Here, we report a strategy to guide polarized light in 2D microflakes by making use of the out-of-plane (OP) orientation of self-trapped excitons in as-synthesized 2D perovskite microplates. A space confined crystallization method is developed to synthesize 2D perovskite microflakes with dominated broad self-trapped excitons emission at room temperature, which are highly OP orientated with a percentage of the OP component over 85%. Taking advantages of the negligible absorption coefficient and improved coupling efficiency of OP orientated self-trapped exciton emission to the planar waveguide mode of the as-synthesized perovskite microflakes, we have achieved a broadband polarized light guiding with a full width at half maximum over 120 nm. Our findings provide a promising platform for the development of ultracompact photonic circuits.

physics.optics↗

arXiv2024

DisDet: Exploring Detectability of Backdoor Attack on Diffusion Models

In the exciting generative AI era, the diffusion model has emerged as a very powerful and widely adopted content generation and editing tool for various data modalities, making the study of their potential security risks very necessary and critical. Very recently, some pioneering works have shown the vulnerability of the diffusion model against backdoor attacks, calling for in-depth analysis and investigation of the security challenges of this popular and fundamental AI technique. In this paper, for the first time, we systematically explore the detectability of the poisoned noise input for the backdoored diffusion models, an important performance metric yet little explored in the existing works. Starting from the perspective of a defender, we first analyze the properties of the trigger pattern in the existing diffusion backdoor attacks, discovering the important role of distribution discrepancy in Trojan detection. Based on this finding, we propose a low-cost trigger detection mechanism that can effectively identify the poisoned input noise. We then take a further step to study the same problem from the attack side, proposing a backdoor attack strategy that can learn the unnoticeable trigger to evade our proposed detection scheme. Empirical evaluations across various diffusion models and datasets demonstrate the effectiveness of the proposed trigger detection and detection-evading attack strategy. For trigger detection, our distribution discrepancy-based solution can achieve a 100\% detection rate for the Trojan triggers used in the existing works. For evading trigger detection, our proposed stealthy trigger design approach performs end-to-end learning to make the distribution of poisoned noise input approach that of benign noise, enabling nearly 100\% detection pass rate with very high attack and benign performance for the backdoored diffusion models.

cs.CR↗

arXiv2023

AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models

Large Vision-Language Models (LVLMs) such as MiniGPT-4 and LLaVA have demonstrated the capability of understanding images and achieved remarkable performance in various visual tasks. Despite their strong abilities in recognizing common objects due to extensive training datasets, they lack specific domain knowledge and have a weaker understanding of localized details within objects, which hinders their effectiveness in the Industrial Anomaly Detection (IAD) task. On the other hand, most existing IAD methods only provide anomaly scores and necessitate the manual setting of thresholds to distinguish between normal and abnormal samples, which restricts their practical implementation. In this paper, we explore the utilization of LVLM to address the IAD problem and propose AnomalyGPT, a novel IAD approach based on LVLM. We generate training data by simulating anomalous images and producing corresponding textual descriptions for each image. We also employ an image decoder to provide fine-grained semantic and design a prompt learner to fine-tune the LVLM using prompt embeddings. Our AnomalyGPT eliminates the need for manual threshold adjustments, thus directly assesses the presence and locations of anomalies. Additionally, AnomalyGPT supports multi-turn dialogues and exhibits impressive few-shot in-context learning capabilities. With only one normal shot, AnomalyGPT achieves the state-of-the-art performance with an accuracy of 86.1%, an image-level AUC of 94.1%, and a pixel-level AUC of 95.3% on the MVTec-AD dataset. Code is available at https://github.com/CASIA-IVA-Lab/AnomalyGPT.

cs.CV↗

arXiv2023

Adaptive Quantization for Key Generation in Low-Power Wide-Area Networks

Physical layer key generation based on reciprocal and random wireless channels has been an attractive solution for securing resource-constrained low-power wide-area networks (LPWANs). When quantizing channel measurements, namely received signal strength indicator (RSSI), into key bits, the existing works mainly adopt fixed quantization levels and guard band parameters, which fail to fully extract keys from RSSI measurements. In this paper, we propose a novel adaptive quantization scheme for key generation in LPWANs, taking LoRa as a case study. The proposed adaptive quantization scheme can dynamically adjust the quantization parameters according to the randomness of RSSI measurements estimated by Lempel-Ziv complexity (LZ76), while ensuring a predefined key disagreement ratio (KDR). Specifically, our scheme uses pre-trained linear regression models to determine the appropriate quantization level and guard band parameter for each segment of RSSI measurements. Moreover, we propose a guard band parameter calibration scheme during information reconciliation during real-time key generation operation. Experimental evaluations using LoRa devices show that the proposed adaptive quantization scheme outperforms the benchmark differential quantization and fixed quantization with up to 2.35$\times$ and 1.51$\times$ key generation rate (KGR) gains, respectively.

eess.SP↗

arXiv2023

Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples

Deep Neural Networks (DNNs) for 3D point cloud recognition are vulnerable to adversarial examples, threatening their practical deployment. Despite the many research endeavors have been made to tackle this issue in recent years, the diversity of adversarial examples on 3D point clouds makes them more challenging to defend against than those on 2D images. For examples, attackers can generate adversarial examples by adding, shifting, or removing points. Consequently, existing defense strategies are hard to counter unseen point cloud adversarial examples. In this paper, we first establish a comprehensive, and rigorous point cloud adversarial robustness benchmark to evaluate adversarial robustness, which can provide a detailed understanding of the effects of the defense and attack methods. We then collect existing defense tricks in point cloud adversarial defenses and then perform extensive and systematic experiments to identify an effective combination of these tricks. Furthermore, we propose a hybrid training augmentation methods that consider various types of point cloud adversarial examples to adversarial training, significantly improving the adversarial robustness. By combining these tricks, we construct a more robust defense framework achieving an average accuracy of 83.45\% against various attacks, demonstrating its capability to enabling robust learners. Our codebase are open-sourced on: \url{https://github.com/qiufan319/benchmark_pc_attack.git}.

cs.CV↗

arXiv2023

BarrierBypass: Out-of-Sight Clean Voice Command Injection Attacks through Physical Barriers

The growing adoption of voice-enabled devices (e.g., smart speakers), particularly in smart home environments, has introduced many security vulnerabilities that pose significant threats to users' privacy and safety. When multiple devices are connected to a voice assistant, an attacker can cause serious damage if they can gain control of these devices. We ask where and how can an attacker issue clean voice commands stealthily across a physical barrier, and perform the first academic measurement study of this nature on the command injection attack. We present the BarrierBypass attack that can be launched against three different barrier-based scenarios termed across-door, across-window, and across-wall. We conduct a broad set of experiments to observe the command injection attack success rates for multiple speaker samples (TTS and live human recorded) at different command audio volumes (65, 75, 85 dB), and smart speaker locations (0.1-4.0m from barrier). Against Amazon Echo Dot 2, BarrierBypass is able to achieve 100% wake word and command injection success for the across-wall and across-window attacks, and for the across-door attack (up to 2 meters). At 4 meters for the across-door attack, BarrierBypass can achieve 90% and 80% injection accuracy for the wake word and command, respectively. Against Google Home mini BarrierBypass is able to achieve 100% wake word injection accuracy for all attack scenarios. For command injection BarrierBypass can achieve 100% accuracy for all the three barrier settings (up to 2 meters). For the across-door attack at 4 meters, BarrierBypass can achieve 80% command injection accuracy. Further, our demonstration using drones yielded high command injection success, up to 100%. Overall, our results demonstrate the potentially devastating nature of this vulnerability to control a user's device from outside of the device's physical space.

cs.CR↗

arXiv2022

EarSpy: Spying Caller Speech and Identity through Tiny Vibrations of Smartphone Ear Speakers

Eavesdropping from the user's smartphone is a well-known threat to the user's safety and privacy. Existing studies show that loudspeaker reverberation can inject speech into motion sensor readings, leading to speech eavesdropping. While more devastating attacks on ear speakers, which produce much smaller scale vibrations, were believed impossible to eavesdrop with zero-permission motion sensors. In this work, we revisit this important line of reach. We explore recent trends in smartphone manufacturers that include extra/powerful speakers in place of small ear speakers, and demonstrate the feasibility of using motion sensors to capture such tiny speech vibrations. We investigate the impacts of these new ear speakers on built-in motion sensors and examine the potential to elicit private speech information from the minute vibrations. Our designed system EarSpy can successfully detect word regions, time, and frequency domain features and generate a spectrogram for each word region. We train and test the extracted data using classical machine learning algorithms and convolutional neural networks. We found up to 98.66% accuracy in gender detection, 92.6% detection in speaker detection, and 56.42% detection in digit detection (which is 5X more significant than the random selection (10%)). Our result unveils the potential threat of eavesdropping on phone conversations from ear speakers using motion sensors.

cs.SD↗

arXiv2022

Efficient electrical switching of exciton states for valley contrast manipulation in two-dimensional perovskite/monolayer WS2 heterostructures

The coupled spin-valley physics in transition metal dichalcogenides (TMDs) endows exciton states with valley degrees of freedom, making them promising for valleytronic applications in TMDs monolayers and/or their heterostructures. Although the valley dynamics of intralayer and interlayer excitons (IXs) have been studied, efficient manipulation of valley pseudospins by switching exciton states remains elusive. Therefore, it is of great importance to effectively tune the exciton states to obtain practical valley polarization switches for valley encoding. Here, we demonstrate the electrical switching of exciton emission with highly variable valley polarization mediated by charged IXs (CIXs) in the heterostructure of monolayer WS2 and two-dimensional (2D) perovskite, irrespective of lattice constants, the rotational and translational alignment. The formation of IXs is identified by photoluminescence excitation (PLE) and photoluminescence (PL) studies, which can be further electrically tuned from positively charged to negatively charged depending on the electrostatic doping level of monolayer WS2. Importantly, we demonstrate an electrical switching from type two to type one band alignment, manifesting as a change in the PL profile from CIX to charged intralayer exciton emission. Such transition induces a large contrast in valley polarization between the two exciton states, enabling the reversible electrically regulated valley polarization switch with a maximum ON/OFF ratio of 15.8. Our study provides an alternative mechanism to achieve valley polarization switching with great simplicity for valleytronics and the electrical control of exciton species and associated valley-contrasting physics would further facilitate the development of optoelectronic and valleytronic devices

physics.app-ph↗

arXiv2022

Privacy-Utility Balanced Voice De-Identification Using Adversarial Examples

Faced with the threat of identity leakage during voice data publishing, users are engaged in a privacy-utility dilemma when enjoying convenient voice services. Existing studies employ direct modification or text-based re-synthesis to de-identify users' voices, but resulting in inconsistent audibility in the presence of human participants. In this paper, we propose a voice de-identification system, which uses adversarial examples to balance the privacy and utility of voice services. Instead of typical additive examples inducing perceivable distortions, we design a novel convolutional adversarial example that modulates perturbations into real-world room impulse responses. Benefit from this, our system could preserve user identity from exposure by Automatic Speaker Identification (ASI) while remaining the voice perceptual quality for non-intrusive de-identification. Moreover, our system learns a compact speaker distribution through a conditional variational auto-encoder to sample diverse target embeddings on demand. Combining diverse target generation and input-specific perturbation construction, our system enables any-to-any identify transformation for adaptive de-identification. Experimental results show that our system could achieve 98% and 79% successful de-identification on mainstream ASIs and commercial systems with an objective Mel cepstral distortion of 4.31dB and a subjective mean opinion score of 4.48.

cs.SD↗

arXiv2022

View-Disentangled Transformer for Brain Lesion Detection

Deep neural networks (DNNs) have been widely adopted in brain lesion detection and segmentation. However, locating small lesions in 2D MRI slices is challenging, and requires to balance between the granularity of 3D context aggregation and the computational complexity. In this paper, we propose a novel view-disentangled transformer to enhance the extraction of MRI features for more accurate tumour detection. First, the proposed transformer harvests long-range correlation among different positions in a 3D brain scan. Second, the transformer models a stack of slice features as multiple 2D views and enhance these features view-by-view, which approximately achieves the 3D correlation computing in an efficient way. Third, we deploy the proposed transformer module in a transformer backbone, which can effectively detect the 2D regions surrounding brain lesions. The experimental results show that our proposed view-disentangled transformer performs well for brain lesion detection on a challenging brain MRI dataset.

cs.CV↗

arXiv2022

RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN

Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models. To date, most of the existing studies focus on backdoor attack against the uncompressed model; while the vulnerability of compressed DNNs, which are widely used in the practical applications, is little exploited yet. In this paper, we propose to study and develop Robust and Imperceptible Backdoor Attack against Compact DNN models (RIBAC). By performing systematic analysis and exploration on the important design knobs, we propose a framework that can learn the proper trigger patterns, model parameters and pruning masks in an efficient way. Thereby achieving high trigger stealthiness, high attack success rate and high model efficiency simultaneously. Extensive evaluations across different datasets, including the test against the state-of-the-art defense mechanisms, demonstrate the high robustness, stealthiness and model efficiency of RIBAC. Code is available at https://github.com/huyvnphan/ECCV2022-RIBAC

cs.CR↗

arXiv2022

UniVIP: A Unified Framework for Self-Supervised Visual Pre-training

Self-supervised learning (SSL) holds promise in leveraging large amounts of unlabeled data. However, the success of popular SSL methods has limited on single-centric-object images like those in ImageNet and ignores the correlation among the scene and instances, as well as the semantic difference of instances in the scene. To address the above problems, we propose a Unified Self-supervised Visual Pre-training (UniVIP), a novel self-supervised framework to learn versatile visual representations on either single-centric-object or non-iconic dataset. The framework takes into account the representation learning at three levels: 1) the similarity of scene-scene, 2) the correlation of scene-instance, 3) the discrimination of instance-instance. During the learning, we adopt the optimal transport algorithm to automatically measure the discrimination of instances. Massive experiments show that UniVIP pre-trained on non-iconic COCO achieves state-of-the-art transfer performance on a variety of downstream tasks, such as image classification, semi-supervised learning, object detection and segmentation. Furthermore, our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2.5% with the same pre-training epochs in linear probing, and surpass current self-supervised object detection methods on COCO dataset, demonstrating its universality and potential.

cs.CV↗

arXiv2022

FewSense, Towards a Scalable and Cross-Domain Wi-Fi Sensing System Using Few-Shot Learning

Wi-Fi sensing can classify human activities because each activity causes unique changes to the channel state information (CSI). Existing WiFi sensing suffers from limited scalability as the system needs to be retrained whenever new activities are added, which cause overheads of data collection and retraining. Cross-domain sensing may fail because the mapping between activities and CSI variations is destroyed when a different environment or user (domain) is involved. This paper proposed a few-shot learning-based WiFi sensing system, named FewSense, which can recognise novel classes in unseen domains with only few samples. Specifically, a feature extractor was pre-trained offline using the source domain data. When the system was applied in the target domain, few samples were used to fine-tune the feature extractor for domain adaptation. Inference was made by computing the cosine similarity. FewSense can further boost the classification accuracy by collaboratively fusing inference from multiple receivers. We evaluated the performance using three public datasets, i.e., SignFi, Widar, and Wiar. The results show that FewSense with five-shot learning recognised novel classes in unseen domains with an accuracy of 90.3\%, 96.5\% ,82.7\% on SignFi, Widar, and Wiar datasets, respectively. Our collaborative sensing model improved system performance by an average of 30\%.

eess.SP↗

arXiv2021

Simultaneous Monitoring of Multiple People's Vital Sign Leveraging a Single Phased-MIMO Radar

Vital sign monitoring plays a critical role in tracking the physiological state of people and enabling various health-related applications (e.g., recommending a change of lifestyle, examining the risk of diseases). Traditional approaches rely on hospitalization or body-attached instruments, which are costly and intrusive. Therefore, researchers have been exploring contact-less vital sign monitoring with radio frequency signals in recent years. Early studies with continuous wave radars/WiFi devices work on detecting vital signs of a single individual, but it still remains challenging to simultaneously monitor vital signs of multiple subjects, especially those who locate in proximity. In this paper, we design and implement a time-division multiplexing (TDM) phased-MIMO radar sensing scheme for high-precision vital sign monitoring of multiple people. Our phased-MIMO radar can steer the mmWave beam towards different directions with a micro-second delay, which enables capturing the vital signs of multiple individuals at the same radial distance to the radar. Furthermore, we develop a TDM-MIMO technique to fully utilize all transmitting antenna (TX)-receiving antenna (RX) pairs, thereby significantly boosting the signal-to-noise ratio. Based on the designed TDM phased-MIMO radar, we develop a system to automatically localize multiple human subjects and estimate their vital signs. Extensive evaluations show that under two-subject scenarios, our system can achieve an error of less than 1 beat per minute (BPM) and 3 BPM for breathing rate (BR) and heartbeat rate (HR) estimations, respectively, at a subject-to-radar distance of $1.6~m$. The minimal subject-to-subject angle separation is $40°$, corresponding to a close distance of $0.5~m$ between two subjects, which outperforms the state-of-the-art.

eess.SP↗